arxivcs.CLcs.AI2026-07-23
RUMBA: Russian User Memory Benchmark
Elizaveta Shevtsova, Inna Glebkina, Mark Baushenko, Pavel Gulyaev, Alena Fenogenova
The ability to handle long-term memory in LLMs is becoming increasingly critical, yet existing benchmarks remain English-centric and rely on aggregate retrieval metrics, failing to capture interactions between long-range context, temporal information, and reasoning. To address th…